Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    chatbot models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     médicas
    1.15
    ickness
    1.15
    ouche
    1.10
    avljen
    1.10
    fficial
    1.09
    üsseldorf
    1.09
    NESDAY
    1.06
     Tuesdays
    1.05
     relativity
    1.05
     pharmacist
    1.05
    POSITIVE LOGITS
     Crest
    1.05
     Ert
    0.89
     berg
    0.86
     CEN
    0.82
     Berg
    0.81
     Hart
    0.80
    Hart
    0.80
    Berg
    0.80
     stein
    0.79
     Bergen
    0.78
    Act Density 0.168%

    No Known Activations